Artificial Intelligence | Evaluating deep learning and radiologist performance in volumetric prostate cancer analysis with biparametric MRI and histopathologically mapped slides

Open Access

10-12-2024 | Artificial Intelligence | Research

Authors: Enis C. Yilmaz, Stephanie A. Harmon, Rosina T. Lis, Omer Tarik Esengur, David G. Gelikman, Marcial Garmendia-Cedillos, Maria J. Merino, Bradford J. Wood, Krishnan Patel, Deborah E. Citrin, Sandeep Gurram, Peter L. Choyke, Peter A. Pinto, Baris Turkbey

Published in:

Abdominal Radiology

Login to get access

Excerpt

In the United States, prostate cancer (PCa) remains the most prevalent non-cutaneous malignancy among biologically male individuals and a significant cause of cancer-related mortality (1). The advent and integration of multiparametric MRI (mpMRI) into the diagnostic and management pathways of PCa have marked a pivotal shift in how the disease is approached. MRI not only facilitates the selection of patients for biopsy by identifying likely cancerous lesions (2) but also guides biopsy needles with high precision (3), thereby enhancing the accuracy of tissue diagnoses. Additionally, MRI plays a crucial role in disease monitoring during active surveillance, treatment decision making, and post-therapy assessment, making it an indispensable tool in the continuum of prostate cancer care (4‐7). …